Related papers: MoE-nD: Per-Layer Mixture-of-Experts Routing for M…

Long-context inference is constrained by KV-cache memory, which grows linearly with sequence length; KV-cache compression therefore hinges on reliably selecting which past tokens to retain. Most geometry-based eviction methods score keys by…

Mixture-of-Experts (MoE) has emerged as a promising architecture for modern large language models (LLMs). However, massive parameters impose heavy GPU memory (i.e., VRAM) demands, hindering the widespread adoption of MoE LLMs. Offloading…

With the breakthrough progress of large language models (LLMs) in natural language processing and multimodal tasks, efficiently deploying them on resource-constrained edge devices has become a critical challenge. The Mixture of Experts…

Key-Value (KV) cache facilitates efficient large language models (LLMs) inference by avoiding recomputation of past KVs. As the batch size and context length increase, the oversized KV caches become a significant memory bottleneck,…

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency,…

Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to be loaded to onboard processing elements during computation.…

The QMoE model provides a practical approach for compression of massive Mixture-of-Experts (MoE) models. QMoE offers a solution geared towards memory limitations that often reach terabyte scales, and it has the advantage of working with…

Key-value~(KV) caching is an important technique to accelerate the inference of large language models~(LLMs), but incurs significant memory overhead. To compress the size of KV cache, existing methods often compromise precision or require…

Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion creates a critical memory bottleneck that fundamentally limits…

Larger transformer models always perform better on various tasks but require more costs to scale up the model size. To efficiently enlarge models, the mixture-of-experts (MoE) architecture is widely adopted, which consists of a gate network…

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…

Transformer-based large language models (LLMs) use the key-value (KV) cache to significantly accelerate inference by storing the key and value embeddings of past tokens. However, this cache consumes significant GPU memory. In this work, we…

Mixture-of-Experts (MoE) models have become a dominant paradigm for scaling large language models, but their rapidly growing parameter sizes introduce a fundamental inefficiency during inference: most expert weights remain idle in GPU…

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…

Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query…

Large Language Models have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache required for long-sequence inference. Recent efforts aim to reduce KV cache size by evicting vast non-critical…

Language models handle increasingly long contexts for tasks such as book summarization, but this leads to growing memory costs for the key-value (KV) cache. Many prior works have proposed ways of discarding KVs from memory, but their…

Long context capability is a crucial competency for large language models (LLMs) as it mitigates the human struggle to digest long-form texts. This capability enables complex task-solving scenarios such as book summarization, code…

Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context inference remains a significant challenge due to the substantial memory requirements…

Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization,…